中文摘要：

随着智能手机和移动互联网的普及，使用智能移动终端进行学习的用户也逐渐增多，移动学习在数字教育领域占据着越来越重要的地位.移动学习的有效性体现在情境感知的能力，即能够感知不同学习情境并提供相应合理的学习内容.因而，移动学习中的情境感知技术已经成为一个研究热点.学习场景的感知是移动学习情境感知的重点，但是由于移动学习的动态性和复杂性，准确的场景感知具有一定的难度.基于实际的移动学习环境，提出了一种根据传感器与学习操作行为对学习场景进行感知分类的方法，处理并分析了由移动学习客户端采集到的传感器数据和学习操作行为日志数据，对比了以传感器数据特征值与学习操作行为特征值共同作为输入特征值的多种场景感知分类算法.结果表明：对比仅使用传感器数据作为分类算法输入特征值的结果，结合学习操作行为日志和传感器数据一起作为学习场景分类感知的依据，可以显著提高移动学习场景的感知分类效果.

英文摘要：

As the popularity of the smart phones and mobile technologies,more and more people beginto use smartphones to learn and get new knowledge.Mobile learning has played a critical role in thefield of education for a few years.The effectiveness of mobile learning reflects in the ability ofperceiving different learning contexts and then provides matched learning resource.Context awarenesshas become a research hotspot,but the most important is learning situation perception.We canprovide proper learning resources according to the specific learning situation.Because of the mobilityand complexity of mobile learning,it5s difficult to perceive learning situation.The thesis proposes amethod to perceive learning situations by combining sensor data and learning operation data andconducts some experiments.It chooses and calculates some sensor data eigenvalues and learningoperation index eigenvalues as the inputs of the classification algorithms?the learning situations thatstudents provide as training set data.The result shows that combining sensor data and learningoperation data to perceive learning situations can improve the accuracy of the learning situationperception,which proves the feasibility and effectiveness of learning situation perception based onsensor data and learning operations.